Scott White
LightNews LightNews
scottswhite.bsky.social
Scott White
@scottswhite.bsky.social
27 followers 59 following 29 posts
Posts Replies Media Videos
Reposted by Scott White
rmcelreath.bsky.social
I'm teaching Statistical Rethinking again starting Jan 2026. This time with live lectures, divided into Beginner and Experienced sections. Will be a lot more work for me, but I hope much better for students.

I will record lectures & all will be found at this link: github.com/rmcelreath/s...
course schedule as a table. Available at the link in the post.
December 9, 2025 at 1:58 PM
Reposted by Scott White
sophieehill.bsky.social
*small domino* my mum tells me not to drink diet coke because she read in the Guardian that it causes dementia

*BIG DOMINO* zoom meeting with the editor-in-chief of Neurology to discuss errors i found in multiple peer-reviewed papers
December 9, 2025 at 4:10 PM
Reposted by Scott White
avehtari.bsky.social
All three books I've co-authored are freely available online for non-commercial use:

- #Bayesian Data Analysis, 3rd ed (aka BDA3) at stat.columbia.edu/~gelman/book/

- #Regression and Other Stories at avehtari.github.io/ROS-Examples/

- Active Statistics at avehtari.github.io/ActiveStatis...
The cover of Bayesian Data Analysis book The cover of Regression and Other Stories book The cover of Active Statistics book
August 2, 2024 at 1:35 PM
Reposted by Scott White
weratedogs.com
This is Millie. She's embarrassed by her new hat. Please help her. 13/10 thanks a bunch (IG: millie.the.boxerr)
a brown boxer sits on the edge of a couch with a stuffed banana toy on her head like a hat. she looks at the camera with wide puppy eyes and a big frown. she finds her situation quite unappeeling.
September 25, 2025 at 4:39 PM
Reposted by Scott White
libbyheeren.bsky.social
Have you played today's #chartle? chartle.cc
Chartle - A daily chart game
Guess the country in red by analysing today's chart
chartle.cc
September 19, 2025 at 5:24 PM
Reposted by Scott White
rmcelreath.bsky.social
I realize the world is burning, but here is the abstract of a talk I will give multiple times in different formats this month. With the feedback, I hope to write up something substantial on the theme in the remainder of the year.
Statistical algorithms have advanced rapidly in the last decades, but most researchers are still only taught how to do t-tests and worry about normality of residuals. At the heart of the reproducibility crisis lies scientific workflow, the often unprincipled and undocumented ways that scientific theories are related to statistical procedures and their results. I want to center scientific workflow in debates about open science and outline a research program for taking scientific workflow seriously.
September 4, 2025 at 7:06 AM
Reposted by Scott White
hauntedtypewriter.bsky.social
librarians are generals in the war on ignorance
August 29, 2025 at 6:15 AM
Reposted by Scott White
dingdingpeng.the100.ci
Ever stared at a table of regression coefficients & wondered what you're doing with your life?

Very excited to share this gentle introduction to another way of making sense of statistical models (w @vincentab.bsky.social)
Preprint: doi.org/10.31234/osf...
Website: j-rohrer.github.io/marginal-psy...
Models as Prediction Machines: How to Convert Confusing Coefficients into Clear Quantities Abstract Psychological researchers usually make sense of regression models by interpreting coefficient estimates directly. This works well enough for simple linear models, but is more challenging for more complex models with, for example, categorical variables, interactions, non-linearities, and hierarchical structures. Here, we introduce an alternative approach to making sense of statistical models. The central idea is to abstract away from the mechanics of estimation, and to treat models as “counterfactual prediction machines,” which are subsequently queried to estimate quantities and conduct tests that matter substantively. This workflow is model-agnostic; it can be applied in a consistent fashion to draw causal or descriptive inference from a wide range of models. We illustrate how to implement this workflow with the marginaleffects package, which supports over 100 different classes of models in R and Python, and present two worked examples. These examples show how the workflow can be applied across designs (e.g., observational study, randomized experiment) to answer different research questions (e.g., associations, causal effects, effect heterogeneity) while facing various challenges (e.g., controlling for confounders in a flexible manner, modelling ordinal outcomes, and interpreting non-linear models). Figure illustrating model predictions. On the X-axis the predictor, annual gross income in Euro. On the Y-axis the outcome, predicted life satisfaction. A solid line marks the curve of predictions on which individual data points are marked as model-implied outcomes at incomes of interest. Comparing two such predictions gives us a comparison. We can also fit a tangent to the line of predictions, which illustrates the slope at any given point of the curve. A figure illustrating various ways to include age as a predictor in a model. On the x-axis age (predictor), on the y-axis the outcome (model-implied importance of friends, including confidence intervals). Illustrated are 1. age as a categorical predictor, resultings in the predictions bouncing around a lot with wide confidence intervals 2. age as a linear predictor, which forces a straight line through the data points that has a very tight confidence band and 3. age splines, which lies somewhere in between as it smoothly follows the data but has more uncertainty than the straight line.
August 25, 2025 at 11:49 AM
Reposted by Scott White
avehtari.bsky.social
Preprint and the website by @dingdingpeng.the100.ci and @vincentab.bsky.social are great, and I got inspired to illustrate Bayesian workflow for model checking and comparison *before* model interpretation following their friendship importance example users.aalto.fi/~ave/casestu...
August 27, 2025 at 10:11 AM
Reposted by Scott White
markrubin.bsky.social
"Understanding different types of review articles: A primer for early career researchers."

By Ghosh & Choudhury (2025)

Open Access: dx.doi.org/10.4103/indi...

#AcademicSky #PhDSky #Methodology
August 26, 2025 at 6:03 PM
Reposted by Scott White
avehtari.bsky.social
Reminder that all three books I've co-authored are freely available online for non-commercial use (and the fourth will be, too)
avehtari.bsky.social Aki Vehtari @avehtari.bsky.social · Aug 2
All three books I've co-authored are freely available online for non-commercial use:

- #Bayesian Data Analysis, 3rd ed (aka BDA3) at stat.columbia.edu/~gelman/book/

- #Regression and Other Stories at avehtari.github.io/ROS-Examples/

- Active Statistics at avehtari.github.io/ActiveStatis...
The cover of Bayesian Data Analysis book The cover of Regression and Other Stories book The cover of Active Statistics book
August 11, 2025 at 5:44 PM
Reposted by Scott White
raulpachecovega.bsky.social
A guiding framework to help learners write more analytically by focusing on the Description, Analysis and Interpretation stages of the research process (GReDAI) www.raulpacheco.org/2025/07/a-gu...

This post is aimed at those of you who have been told "you need to write more analytically"

#RPVSky
A guiding framework to help learners write more analytically by focusing on the Description, Analysis and Interpretation stages of the research process (GReDAI)
Three of my PhD students are nearing completion of their final doctoral dissertation drafts, and
www.raulpacheco.org
July 28, 2025 at 11:09 AM
Reposted by Scott White
raulpachecovega.bsky.social
“I'm writing a first draft and reminding myself that I'm simply shovelling sand into a box so that later I can build castles.”
― Shannon Hale

#WritingSky #AcademicSky
May 20, 2025 at 11:12 AM
Reposted by Scott White
rhigarthjones.bsky.social
I read this poem at my godmother's funeral - her daughter picked it for me, I hadn't come across it before that.

It's such a beautiful poem, I go back to it quite regularly now and think about all the people who sheltered me with their raincoats.
groversbathtub.bsky.social Grover’s Bathtub @groversbathtub.bsky.social · May 11
Your post reminded me of this poem by Ada Limón:
THE RAINCOAT When the doctor suggested surgery and a brace for all my youngest years, my parents scrambled to take me to massage therapy, deep tissue work, osteopathy, and soon my crooked spine unspooled a bit, I could breathe again, and move more in a body unclouded by pain. My mom would tell me to sing songs to her the whole forty-five-minute drive to Middle Two Rock Road and forty-five minutes back from physical therapy. She'd say that even my voice sounded unfettered by my spine afterward. So 1 sang and sang, because I thought she liked it. I never asked her what she gave up to drive me, or how her day was before this chore. Today, at her age, I was driving myself home from yet another spine appointment, singing along to some maudlin but solid song on the radio, and I saw a mom take her raincoat off and give it to her young daughter when a storm took over the afternoon. My god, I thought, my whole life I've been under her raincoat thinking it was somehow a marvel that I never got wet.
May 11, 2025 at 3:30 PM
Reposted by Scott White
paolopalma.bsky.social
Tried to argue against a scale one time and was met with "this is a frequently used scale" like I wasn't gonna say "well they were wrong too"
Excerpt from the web page linked in the quote tweet: The Loyalist “We’ve used this survey for years. We have benchmark data.” They trust the legacy. They don’t want to lose the trend line. And they assume that if it worked before, it must still be working now. But familiarity doesn’t equal quality. And even data that is benchmarked can still be bad.
May 7, 2025 at 3:11 PM
Reposted by Scott White
dliebl.com
Grace Wahba, "the mother of smoothing splines," won the International Prize (aka the Nobel) in Statistics #stats for her representer theorem.
youtu.be/8Ae_QzwwR_U?...

So well deserved! I guess, one could also give her the price again in two years for her work on Generalized Cross-Validation.
Foto of Grace Whaba. Grace Wahba's award winning paper.
May 4, 2025 at 5:01 PM
Reposted by Scott White
sbmost.bsky.social
Daughter was down about the state of the world.
“If someone lit a match on that hilltop,” I said, “would you see it?”
“No”
“Would you if it was at night?”
“Probably”
“The darker the world, the more the bits of good we do make a difference.”

Dear reader, she was almost as impressed with me as I was.
April 28, 2025 at 5:43 AM
Reposted by Scott White
f2harrell.bsky.social
Bayesian joint modeling for multiple clinical outcome variables is highly promising. I can’t wait to read this. #StatsSky #rct
April 28, 2025 at 11:39 AM
Reposted by Scott White
dariia.bsky.social
If you are not personally interested in attending this workshop, you can also sponsor participation of students!
Details: bit.ly/3wBeY4S
Please share!
#AcademicSky #EconSky #RStats #dataviz
dariia.bsky.social Dariia Mykhailyshyna @dariia.bsky.social · Apr 26
❗️Our next workshop will be on May 1st, 6 pm CEST on Smart Extraction: converting PDF tables into usable data with R by @flaviaerius.bsky.social!
Register or sponsor a student by donating to support Ukraine!
Details: bit.ly/3wBeY4S
Please share!
#AcademicSky #EconSky #RStats #dataviz
April 27, 2025 at 8:54 AM
scottswhite.bsky.social
Favourite writing analogy thus far.
raulpachecovega.bsky.social Raul Pacheco-Vega @raulpachecovega.bsky.social · Apr 26
“I'm writing a first draft and reminding myself that I'm simply shovelling sand into a box so that later I can build castles.”
― Shannon Hale

#WritingSky #AcademicSky
April 27, 2025 at 7:04 AM
Reposted by Scott White
jonpuritz.marineevoeco.com
xkcd.com/3081
XKCD comic about PhD timelines making a political statement about illegal student seizures and illegal imprisonment of foreign students.
April 25, 2025 at 6:19 PM
Reposted by Scott White
tjmahr.com
no, we are bottling up magic spells 😉 www.tjmahr.com/set-na-where...
set_na_where(): a nonstandard evaluation use case
Bottling up magic spells
www.tjmahr.com
April 25, 2025 at 8:12 PM
Reposted by Scott White
kellybodwin.com
New unhinged #rstats rant about NSE just dropped:

🔗 kbodwin.github.io/paRticles/po...

tl;dr - some cute (?) tricks for iterating over unquoted columns

see below to skip the stream-of-consiousness blog and go straight to code snippets
Punctuation and Other Problems – paRticles
kbodwin.github.io
April 25, 2025 at 6:30 AM
Reposted by Scott White
epiellie.bsky.social
FACT CHECK:

This viral graph from twitter claims to *prove* vaccines cause autism.

But there's something fishy about the data! Let's dive in.
April 22, 2025 at 4:25 PM